Improved Prediction of Blood–Brain Barrier Permeability Through Machine Learning with Combined Use of Molecular Property-Based Descriptors and Fingerprints

Blood–brain barrier (BBB) permeability of a compound determines whether the compound can effectively enter the brain. It is an essential property which must be accounted for in drug discovery with a target in the brain. Several computational methods have been used to predict the BBB permeability. In particular, support vector machine (SVM), which is a kernel-based machine learning method, has been used popularly in this field. For SVM training and prediction, the compounds are characterized by molecular descriptors. Some SVM models were based on the use of molecular property-based descriptors (including 1D, 2D, and 3D descriptors) or fragment-based descriptors (known as the fingerprints of a molecule). The selection of descriptors is critical for the performance of a SVM model. In this study, we aimed to develop a generally applicable new SVM model by combining all of the features of the molecular property-based descriptors and fingerprints to improve the accuracy for the BBB permeability prediction. The results indicate that our SVM model has improved accuracy compared to the currently available models of the BBB permeability prediction.

[1]  P. Mahadevan,et al.  An overview , 2007, Journal of Biosciences.

[2]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[3]  Fang Zheng,et al.  Computational neural network analysis of the affinity of N-n-alkylnicotinium salts for the α4β2* nicotinic acetylcholine receptor , 2009 .

[4]  Carolyn R. Bertozzi,et al.  Methods and Applications , 2009 .

[5]  Mehrdad Hamidi,et al.  Brain drug targeting: a computational approach for overcoming blood-brain barrier. , 2009, Drug discovery today.

[6]  Hanna Geppert,et al.  Current Trends in Ligand-Based Virtual Screening: Molecular Representations, Data Mining Methods, New Application Areas, and Performance Evaluation , 2010, J. Chem. Inf. Model..

[7]  Juan M. Luco,et al.  Prediction of the Brain—Blood Distribution of a Large Set of Drugs from Structurally Derived Descriptors Using Partial Least-Squares (PLS) Modeling. , 2010 .

[8]  Prabha Garg,et al.  In Silico Prediction of Blood Brain Barrier Permeability: An Artificial Neural Network Model , 2006, J. Chem. Inf. Model..

[9]  Gilberto Alves,et al.  Blood-brain barrier models and their relevance for a successful development of CNS drug delivery systems: a review. , 2014, European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V.

[10]  L. Dwoskin,et al.  QSAR study on maximal inhibition (Imax) of quaternary ammonium antagonists for S-(-)-nicotine-evoked dopamine release from dopaminergic nerve terminals in rat striatum. , 2009, Bioorganic & medicinal chemistry.

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  A. Avdeef,et al.  P-glycoprotein deficient mouse in situ blood-brain barrier permeability and its prediction using an in combo PAMPA model. , 2009, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[13]  Santiago Vilar,et al.  Prediction of passive blood-brain partitioning: straightforward and effective classification models based on in silico derived physicochemical descriptors. , 2010, Journal of molecular graphics & modelling.

[14]  Zhi-Wei Cao,et al.  Effect of Selection of Molecular Descriptors on the Prediction of Blood-Brain Barrier Penetrating and Nonpenetrating Agents by Statistical Learning Methods , 2005, J. Chem. Inf. Model..

[15]  M. W. B. Trotter,et al.  Support vector machines for drug discovery , 2007 .

[16]  Bernard Testa,et al.  A simple model to predict blood-brain barrier permeation from 3D molecular fields. , 2002, Biochimica et biophysica acta.

[17]  Li Di,et al.  Strategies to assess blood–brain barrier penetration , 2008, Expert opinion on drug discovery.

[18]  B Testa,et al.  Predicting blood-brain barrier permeation from three-dimensional molecular structure. , 2000, Journal of medicinal chemistry.

[19]  L. Dwoskin,et al.  QSAR modeling of mono- and bis-quaternary ammonium salts that act as antagonists at neuronal nicotinic acetylcholine receptors mediating dopamine release. , 2006, Bioorganic & medicinal chemistry.

[20]  D. E. Clark.  In silico prediction of blood-brain barrier permeation. , 2003, Drug discovery today.

[21]  Fang Zheng,et al.  Computational neural network analysis of the affinity of lobeline and tetrabenazine analogs for the vesicular monoamine transporter-2. , 2007, Bioorganic & medicinal chemistry.

[22]  Hassan Golmohammadi,et al.  Quantitative structure-activity relationship prediction of blood-to-brain partitioning behavior using support vector machine. , 2012, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[23]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[24]  Sarel F Malan,et al.  Physicochemical prediction of a brain-blood distribution profile in polycyclic amines. , 2003, Bioorganic & medicinal chemistry.

[25]  Tingjun Hou,et al.  ADME evaluation in drug discovery , 2002, Journal of molecular modeling.

[26]  A George.  The design and molecular modeling of CNS drugs. , 1999, Current opinion in drug discovery & development.

[27]  Samy Bengio,et al.  SVMTorch: Support Vector Machines for Large-Scale Regression Problems , 2001, J. Mach. Learn. Res..

[28]  Remigijus Didziapetris,et al.  QSAR analysis of blood-brain distribution: the influence of plasma and brain tissue binding. , 2011, Journal of pharmaceutical sciences.

[29]  Yun Tang,et al.  In SilicoPrediction of Blood–Brain Partitioning Using a Chemometric Method Called Genetic Algorithm Based Variable Selection , 2008 .

[30]  Pierre Baldi,et al.  Assessing the accuracy of prediction algorithms for classification: an overview , 2000, Bioinform..

[31]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[32]  Jie Shen,et al.  Estimation of ADME Properties with Substructure Pattern Recognition , 2010, J. Chem. Inf. Model..

[33]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[34]  Remigijus Didziapetris,et al.  Improving the prediction of drug disposition in the brain , 2013, Expert opinion on drug metabolism & toxicology.

[35]  P. Crooks,et al.  Improving the inhibitory activity of arylidenaminoguanidine compounds at the N-methyl-D-aspartate receptor complex from a recursive computational-experimental structure-activity relationship study. , 2013, Bioorganic & medicinal chemistry.

[36]  Franco Lombardo,et al.  A recursive-partitioning model for blood–brain barrier permeation , 2005, J. Comput. Aided Mol. Des..

[37]  Tingjun Hou,et al.  ADME Evaluation in Drug Discovery, 8. The Prediction of Human Intestinal Absorption by a Support Vector Machine , 2007, J. Chem. Inf. Model..

[38]  Alexander Golbraikh,et al.  QSAR Modeling of the Blood–Brain Barrier Permeability for Diverse Organic Compounds , 2008, Pharmaceutical Research.

[39]  D. Mishra,et al.  Drug targeting to brain: a systematic approach to study the factors, parameters and approaches for prediction of permeability of drugs across BBB , 2013, Expert opinion on drug delivery.

[40]  Chih-Jen Lin,et al.  Radius Margin Bounds for Support Vector Machines with the RBF Kernel , 2002, Neural Computation.

[41]  Mark L. Lewis,et al.  Predicting Penetration Across the Blood-Brain Barrier from Simple Descriptors and Fragmentation Schemes , 2007, J. Chem. Inf. Model..

[42]  L. Dwoskin,et al.  Computational neural network analysis of the affinity of N-n-alkylnicotinium salts for the alpha4beta2* nicotinic acetylcholine receptor. , 2009, Journal of enzyme inhibition and medicinal chemistry.

[43]  CHUN WEI YAP,et al.  PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprints , 2011, J. Comput. Chem..

[44]  Marc Adenot,et al.  Blood‐Brain Barrier Permeation Models: Discriminating Between Potential CNS and Non‐CNS Drugs Including P‐Glycoprotein Substrates. , 2004 .

[45]  Andreas Zell,et al.  Kernel Functions for Attributed Molecular Graphs – A New Similarity‐Based Approach to ADME Prediction in Classification and Regression , 2006 .

[46]  L. Hall,et al.  Modeling Blood-Brain Barrier Partitioning Using the Electrotopological State. , 2002 .

[47]  L. A. Stone,et al.  Computer Aided Design of Experiments , 1969 .

[48]  Michael H Abraham,et al.  The factors that influence permeation across the blood-brain barrier. , 2004, European journal of medicinal chemistry.

[49]  Seung-Hoon Choi,et al.  Artificial neural network models for prediction of intestinal permeability of oligopeptides , 2007, BMC Bioinformatics.

[50]  Remigijus Didziapetris,et al.  Ionization-specific prediction of blood-brain permeability. , 2009, Journal of pharmaceutical sciences.

[51]  R Griffiths,et al.  Development of a new physicochemical model for brain penetration and its application to the design of centrally acting H2 receptor histamine antagonists. , 1988, Journal of medicinal chemistry.